Skip to content
This repository has been archived by the owner on Nov 18, 2023. It is now read-only.

pytorch support #44

Closed
geoHeil opened this issue Feb 4, 2019 · 3 comments
Closed

pytorch support #44

geoHeil opened this issue Feb 4, 2019 · 3 comments
Assignees
@jmsfltchr
Labels
status: solved type: feature
Milestone
KGLIB: Transform ...

Comments

@geoHeil
Copy link

geoHeil commented Feb 4, 2019

Hi,

do you plan to add support for pytorch models?
@jmsfltchr jmsfltchr self-assigned this Feb 4, 2019
@jmsfltchr
Copy link
Contributor

Hi @geoHeil,

PyTorch isn't planned currently. What's the use-case that you have in mind?
For instance, are you integrating with an existing pipeline, or prefer the features of PyTorch?

@jmsfltchr
Copy link
Contributor

Closing due to inactivity

@jmsfltchr jmsfltchr reopened this Jun 15, 2022
@jmsfltchr jmsfltchr mentioned this issue Jul 8, 2022
Merged
lolski pushed a commit that referenced this issue Jul 28, 2022
@jmsfltchr
Pytorch Geometric support (deprecates KGCN) (#161)
57ccda7 
## What is the goal of this PR?

Migrate the ethos of TypeDB-ML to be a library to support machine learning using existing graph learning frameworks, starting with support for [PyTorch Geometric](https://github.com/pyg-team/pytorch_geometric) and [NetworkX](https://networkx.org) to support in-memory graphs and general-purpose graph algorithms.

## What are the changes implemented in this PR?

- Encoding of a TypeDB graph (already exported into NetworkX) into a PyTorch Geometric HeteroData object
- Updating the Diagnosis example to demonstrate how to create a GNN using TypeDB, KGLIB and PyTorch Geometric

Solves #44
@jmsfltchr
Copy link
Contributor

Completed in #161

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees

@jmsfltchr jmsfltchr

Labels
status: solved type: feature
Projects
None yet
Milestone
KGLIB: Transform to ML Library Integr...
Development

No branches or pull requests
3 participants
@geoHeil @jmsfltchr @grabl